Howard881010 commited on
Commit
86f4d6a
·
verified ·
1 Parent(s): 19de533

End of training

Browse files
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: allenai/longformer-base-4096
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: longformer-combined-2epoch
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # longformer-combined-2epoch
19
+
20
+ This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.4259
23
+ - Accuracy: 0.71
24
+ - F1: 0.6410
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 20
45
+ - eval_batch_size: 20
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
55
+ | 0.7476 | 0.0556 | 50 | 0.7044 | 0.494 | 0.3308 |
56
+ | 0.7543 | 0.1111 | 100 | 0.7187 | 0.5215 | 0.3427 |
57
+ | 0.6395 | 0.1667 | 150 | 0.7392 | 0.5215 | 0.3427 |
58
+ | 0.6322 | 0.2222 | 200 | 0.5797 | 0.648 | 0.5771 |
59
+ | 0.5879 | 0.2778 | 250 | 0.5351 | 0.678 | 0.5905 |
60
+ | 0.5179 | 0.3333 | 300 | 0.5117 | 0.6975 | 0.6116 |
61
+ | 0.5868 | 0.3889 | 350 | 0.5010 | 0.704 | 0.6184 |
62
+ | 0.4915 | 0.4444 | 400 | 0.4662 | 0.72 | 0.6348 |
63
+ | 0.5408 | 0.5 | 450 | 0.5064 | 0.67 | 0.5990 |
64
+ | 0.4393 | 0.5556 | 500 | 0.4584 | 0.6965 | 0.6271 |
65
+ | 0.4974 | 0.6111 | 550 | 0.4894 | 0.688 | 0.6183 |
66
+ | 0.461 | 0.6667 | 600 | 0.4711 | 0.688 | 0.6184 |
67
+ | 0.4446 | 0.7222 | 650 | 0.4520 | 0.719 | 0.6338 |
68
+ | 0.4059 | 0.7778 | 700 | 0.5283 | 0.703 | 0.6166 |
69
+ | 0.4914 | 0.8333 | 750 | 0.4977 | 0.6655 | 0.5949 |
70
+ | 0.4506 | 0.8889 | 800 | 0.4973 | 0.7155 | 0.6303 |
71
+ | 0.4433 | 0.9444 | 850 | 0.4571 | 0.6935 | 0.6239 |
72
+ | 0.5217 | 1.0 | 900 | 0.4675 | 0.6875 | 0.6177 |
73
+ | 0.5323 | 1.0556 | 950 | 0.4639 | 0.691 | 0.6213 |
74
+ | 0.4469 | 1.1111 | 1000 | 0.4869 | 0.6815 | 0.6116 |
75
+ | 0.4435 | 1.1667 | 1050 | 0.4606 | 0.698 | 0.6286 |
76
+ | 0.4596 | 1.2222 | 1100 | 0.4464 | 0.7235 | 0.6384 |
77
+ | 0.4454 | 1.2778 | 1150 | 0.4574 | 0.6985 | 0.6291 |
78
+ | 0.4308 | 1.3333 | 1200 | 0.4343 | 0.7295 | 0.6446 |
79
+ | 0.4656 | 1.3889 | 1250 | 0.4517 | 0.7235 | 0.6384 |
80
+ | 0.4057 | 1.4444 | 1300 | 0.4412 | 0.7035 | 0.6343 |
81
+ | 0.4322 | 1.5 | 1350 | 0.4306 | 0.7035 | 0.6343 |
82
+ | 0.417 | 1.5556 | 1400 | 0.4269 | 0.7305 | 0.6457 |
83
+ | 0.3974 | 1.6111 | 1450 | 0.4333 | 0.7295 | 0.6447 |
84
+ | 0.41 | 1.6667 | 1500 | 0.4340 | 0.7045 | 0.6354 |
85
+ | 0.4132 | 1.7222 | 1550 | 0.4532 | 0.7005 | 0.6312 |
86
+ | 0.445 | 1.7778 | 1600 | 0.4399 | 0.733 | 0.6482 |
87
+ | 0.4159 | 1.8333 | 1650 | 0.4374 | 0.7325 | 0.6477 |
88
+ | 0.3858 | 1.8889 | 1700 | 0.4234 | 0.735 | 0.6503 |
89
+ | 0.4641 | 1.9444 | 1750 | 0.4244 | 0.737 | 0.6524 |
90
+ | 0.3893 | 2.0 | 1800 | 0.4259 | 0.71 | 0.6410 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.46.0
96
+ - Pytorch 2.4.0+cu121
97
+ - Datasets 2.21.0
98
+ - Tokenizers 0.20.1
logs/events.out.tfevents.1737657261.yadi.2783404.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81685476059c9db9721499517b9c7d4ef601a1e83591bcfa9b4b8ce52741617f
3
- size 56657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cfd6145d3145b1fc01f9cfe529c43f13c085f1dd11e60ee625f23c318530e9
3
+ size 57011
logs/events.out.tfevents.1737661034.yadi.2783404.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4282286a438383213134fe17fe22a776aec06919e5c4d152e5adfed574489244
3
+ size 457
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "LongformerTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff